• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Uma abordagem não supervisionada para classificação de opinião usando o recurso léxico SentiWordNet

CAVALCANTI, Diana Cabral 31 January 2011 (has links)
Made available in DSpace on 2014-06-12T15:49:49Z (GMT). No. of bitstreams: 2 arquivo1261_1.pdf: 2414749 bytes, checksum: c01ef58dbd0f4ac1de0693518c0b51f4 (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2011 / Mineração de Opinião, também chamada de Análise de Sentimento, explora o estudo computacional de opiniões, sentimentos e emoções expressadas em fontes como textos não estruturados. Com a crescente popularidade e disponibilidade de recursos para se veicular opiniões na Web, os internautas passaram a ser não só um mero consumidor de um produto já pronto, mas também um gerador de conteúdo na Web. A classificação de sentimento tem o desafio de automatizar a análise de opiniões na Web, a fim de colaborar na forma como as pessoas podem, fazem e usam ativamente as tecnologias de informação para buscar e compreender as opiniões dos outros. Diversas pesquisas têm explorado métodos supervisionados e não supervisionados para classificação de sentimento que abrangem técnicas de processamento de linguagem natural, recuperação da informação e recursos léxicos. Este trabalho propõe o uso do recurso Léxico SentiWordNet, com um método não supervisionado, que realiza a seleção de termos unigrama nas classes gramaticais adjetivo, advérbio, substantivo e verbo, para classificar a polaridade, se negativa, positiva ou neutra, de termos e documentos. A fim de avaliar o desempenho do método, experimentos foram realizados em duas bases de dados, que abrangem comentários extraídos do Amazon.com e citações em artigos científicos. Os resultados obtidos experimentalmente mostraram que o SentiWordNet atingiu uma média de 76% para o total de termos distintos extraídos, a maior taxa de acerto global foi 58% para a base de documentos do Amazon.com e 18.83% para a base de artigos científicos
2

Contextual lexicon-based sentiment analysis for social media

Muhammad, Aminu January 2016 (has links)
Sentiment analysis concerns the computational study of opinions expressed in text. Social media domains provide a wealth of opinionated data, thus, creating a greater need for sentiment analysis. Typically, sentiment lexicons that capture term-sentiment association knowledge are commonly used to develop sentiment analysis systems. However, the nature of social media content calls for analysis methods and knowledge sources that are better able to adapt to changing vocabulary. Invariably existing sentiment lexicon knowledge cannot usefully handle social media vocabulary which is typically informal and changeable yet rich in sentiment. This, in turn, has implications on the analyser's ability to effectively capture the context therein and to interpret the sentiment polarity from the lexicons. In this thesis we use SentiWordNet, a popular sentiment-rich lexicon with a substantial vocabulary coverage and explore how to adapt it for social media sentiment analysis. Firstly, the thesis identifies a set of strategies to incorporate the effect of modifiers on sentiment-bearing terms (local context). These modifiers include: contextual valence shifters, non-lexical sentiment modifiers typical in social media and discourse structures. Secondly, the thesis introduces an approach in which a domain-specific lexicon is generated using a distant supervision method and integrated with a general-purpose lexicon, using a weighted strategy, to form a hybrid (domain-adapted) lexicon. This has the dual purpose of enriching term coverage of the general purpose lexicon with non-standard but sentiment-rich terms as well as adjusting sentiment semantics of terms. Here, we identified two term-sentiment association metrics based on Term Frequency and Inverse Document Frequency that are able to outperform the state-of-the-art Point-wise Mutual Information on social media data. As distant supervision may not be readily applicable on some social media domains, we explore the cross-domain transferability of a hybrid lexicon. Thirdly, we introduce an approach for improving distant-supervised sentiment classification with knowledge from local context analysis, domain-adapted (hybrid) and emotion lexicons. Finally, we conduct a comprehensive evaluation of all identified approaches using six sentiment-rich social media datasets.

Page generated in 0.0407 seconds